Modelling and forecasting reservoir sedimentation of irrigation dams in the Guinea Savannah Ecological Zone of Ghana

Effective management of reservoir sedimentation requires models that can predict sedimentation of the reservoirs. In this study, linear regression, non-linear exponential regression and artificial neural network models have been developed for the forecasting of annual storage capacity loss of reserv...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Thomas Apusiga Adongo, Felix K. Abagale, Wilson A. Agyare
Formato:	article
Lenguaje:	EN
Publicado:	IWA Publishing 2021
Materias:	artificial neural network forecasting irrigation dams linear regression nonlinear exponential regression reservoir sedimentation modelling Environmental technology. Sanitary engineering TD1-1066
Acceso en línea:	https://doaj.org/article/cd14636832a64a889380329401918e1c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:cd14636832a64a889380329401918e1c
record_format	dspace
spelling	oai:doaj.org-article:cd14636832a64a889380329401918e1c2021-11-05T21:17:14ZModelling and forecasting reservoir sedimentation of irrigation dams in the Guinea Savannah Ecological Zone of Ghana1751-231X10.2166/wpt.2021.073https://doaj.org/article/cd14636832a64a889380329401918e1c2021-10-01T00:00:00Zhttp://wpt.iwaponline.com/content/16/4/1355https://doaj.org/toc/1751-231XEffective management of reservoir sedimentation requires models that can predict sedimentation of the reservoirs. In this study, linear regression, non-linear exponential regression and artificial neural network models have been developed for the forecasting of annual storage capacity loss of reservoirs in the Guinea Savannah Ecological Zone (GSEZ) of Ghana. Annual rainfall, inflows, trap efficiency and reservoir age were input parameters for the models whilst the output parameter was the annual sediment volume in the reservoirs. Twenty (20) years of reservoirs data with 70% data used for model training and 30% used for validation. The ANN model, the feed-forward, back-propagation algorithm Multi-Layer Perceptron model structure which best captured the pattern in the annual sediment volumes retained in the reservoirs ranged from 4-6-1 at Karni to 4-12-1 at Tono. The linear and nonlinear exponential regression models revealed that annual sediment volume retention increased with all four (4) input parameters whilst the rate of sedimentation in the reservoirs is a decreasing function of time. All the three (3) models developed were noted to be efficient and suitable for forecasting annual sedimentation of the studied reservoirs with accuracies above 76%. Forecasted sedimentation up to year 2038 (2019–2038) using the developed models revealed the total storage capacities of the reservoirs to be lost ranged from 13.83 to 50.07%, with 50% of the small and medium reservoirs filled with sediment deposits if no sedimentation control measures are taken to curb the phenomenon. HIGHLIGHTS The study developed two mathematical models using linear regression.; The study developed non-linear exponential regression.; The study developed an artificial neural network (ANN) model.; The study forecasted sedimentation up to year 2038 using the developed models.; The study revealed that the total storage capacities of the reservoirs to be lost ranged from 13.83 to 50.07%.;Thomas Apusiga AdongoFelix K. AbagaleWilson A. AgyareIWA Publishingarticleartificial neural networkforecastingirrigation damslinear regressionnonlinear exponential regressionreservoir sedimentation modellingEnvironmental technology. Sanitary engineeringTD1-1066ENWater Practice and Technology, Vol 16, Iss 4, Pp 1355-1369 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	artificial neural network forecasting irrigation dams linear regression nonlinear exponential regression reservoir sedimentation modelling Environmental technology. Sanitary engineering TD1-1066
spellingShingle	artificial neural network forecasting irrigation dams linear regression nonlinear exponential regression reservoir sedimentation modelling Environmental technology. Sanitary engineering TD1-1066 Thomas Apusiga Adongo Felix K. Abagale Wilson A. Agyare Modelling and forecasting reservoir sedimentation of irrigation dams in the Guinea Savannah Ecological Zone of Ghana
description	Effective management of reservoir sedimentation requires models that can predict sedimentation of the reservoirs. In this study, linear regression, non-linear exponential regression and artificial neural network models have been developed for the forecasting of annual storage capacity loss of reservoirs in the Guinea Savannah Ecological Zone (GSEZ) of Ghana. Annual rainfall, inflows, trap efficiency and reservoir age were input parameters for the models whilst the output parameter was the annual sediment volume in the reservoirs. Twenty (20) years of reservoirs data with 70% data used for model training and 30% used for validation. The ANN model, the feed-forward, back-propagation algorithm Multi-Layer Perceptron model structure which best captured the pattern in the annual sediment volumes retained in the reservoirs ranged from 4-6-1 at Karni to 4-12-1 at Tono. The linear and nonlinear exponential regression models revealed that annual sediment volume retention increased with all four (4) input parameters whilst the rate of sedimentation in the reservoirs is a decreasing function of time. All the three (3) models developed were noted to be efficient and suitable for forecasting annual sedimentation of the studied reservoirs with accuracies above 76%. Forecasted sedimentation up to year 2038 (2019–2038) using the developed models revealed the total storage capacities of the reservoirs to be lost ranged from 13.83 to 50.07%, with 50% of the small and medium reservoirs filled with sediment deposits if no sedimentation control measures are taken to curb the phenomenon. HIGHLIGHTS The study developed two mathematical models using linear regression.; The study developed non-linear exponential regression.; The study developed an artificial neural network (ANN) model.; The study forecasted sedimentation up to year 2038 using the developed models.; The study revealed that the total storage capacities of the reservoirs to be lost ranged from 13.83 to 50.07%.;
format	article
author	Thomas Apusiga Adongo Felix K. Abagale Wilson A. Agyare
author_facet	Thomas Apusiga Adongo Felix K. Abagale Wilson A. Agyare
author_sort	Thomas Apusiga Adongo
title	Modelling and forecasting reservoir sedimentation of irrigation dams in the Guinea Savannah Ecological Zone of Ghana
title_short	Modelling and forecasting reservoir sedimentation of irrigation dams in the Guinea Savannah Ecological Zone of Ghana
title_full	Modelling and forecasting reservoir sedimentation of irrigation dams in the Guinea Savannah Ecological Zone of Ghana
title_fullStr	Modelling and forecasting reservoir sedimentation of irrigation dams in the Guinea Savannah Ecological Zone of Ghana
title_full_unstemmed	Modelling and forecasting reservoir sedimentation of irrigation dams in the Guinea Savannah Ecological Zone of Ghana
title_sort	modelling and forecasting reservoir sedimentation of irrigation dams in the guinea savannah ecological zone of ghana
publisher	IWA Publishing
publishDate	2021
url	https://doaj.org/article/cd14636832a64a889380329401918e1c
work_keys_str_mv	AT thomasapusigaadongo modellingandforecastingreservoirsedimentationofirrigationdamsintheguineasavannahecologicalzoneofghana AT felixkabagale modellingandforecastingreservoirsedimentationofirrigationdamsintheguineasavannahecologicalzoneofghana AT wilsonaagyare modellingandforecastingreservoirsedimentationofirrigationdamsintheguineasavannahecologicalzoneofghana
_version_	1718444009439887360

Modelling and forecasting reservoir sedimentation of irrigation dams in the Guinea Savannah Ecological Zone of Ghana

Ejemplares similares